One machine-learning technique is to pit evolving neural networks against each other in cage matches and then learn from the results. This is called Generative Adversarial Networks (GANs).
At yesterday's Purim festivities somebody described the following cutting-edge research, and I remembered just enough keywords to be able to find the paper later:
Stopping GAN Violence: Generative Unadversarial Networks Samuel Albanie, Sébastien Ehrhardt, João F. Henriques While the costs of human violence have attracted a great deal of attention from the research community, the effects of the network-on-network (NoN) violence popularised by Generative Adversarial Networks have yet to be addressed. In this work, we quantify the financial, social, spiritual, cultural, grammatical and dermatological impact of this aggression and address the issue by proposing a more peaceful approach which we term Generative Unadversarial Networks (GUNs). Under this framework, we simultaneously train two models: a generator G that does its best to capture whichever data distribution it feels it can manage, and a motivator M that helps G to achieve its dream. Fighting is strictly verboten and both models evolve by learning to respect their differences. The framework is both theoretically and electrically grounded in game theory, and can be viewed as a winner-shares-all two-player game in which both players work as a team to achieve the best score. Experiments show that by working in harmony, the proposed model is able to claim both the moral and log-likelihood high ground. Our work builds on a rich history of carefully argued position-papers, published as anonymous YouTube comments, which prove that the optimal solution to NoN violence is more GUNs.
I haven't read the full paper yet, but on a quick skim it does not disappoint. More info.
I'm delighted to see that the paper was submitted to SIGBOVIK 2017. I had no idea that Dr. Bovik had his own SIG.
ETA: Not only was that paper submitted to SIGBOVIK, but SIGBOVIK is a real thing. How did I not know about this gem from my alma mater? (Sadly, this year's conference starts at 5PM on a Friday, which would be challenging. Maybe I'll have better luck next year.)